• m-bain/whisperX: WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
• NeuSpeech awesome-brain-decoding: collection of awesome research in brain decoding, including interaction with multi-modalities, theories, and foundation models.
• Feature Discovery in Audio Models
• NVIDIA personaplex - PersonaPlex code.
• no build in drac slurm
• Mechanistic Interpretability for AI Safety A Review
• C. West Churchman's Systems Epistemology and LLMs
• Investigating the concept of representation in the neural and psychological sciences
• distillation can lead to subliminal learning
• Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
• Omni-iEEG: A Large-Scale, Comprehensive iEEG Dataset and Benchmark for Epilepsy Research
• agentmemory: #1 Persistent memory for AI coding agents based on real-world benchmarks
• GLM-ASR-Nano-2512
• Omni-iEEG openreview A Large-Scale, Comprehensive iEEG Dataset and Benchmark...
• check start time slurm drac compute canada
• Lorem ipsum
• I gave Claude Code a $0.02/call coworker and stopped hitting Pro limits — here's the full setup
• using tmux
• Emergence explains nothing and is bad science
• datalab-to marker Convert PDF to markdown plus JSON quickly with high accuracy
• A Survey on Speech Large Language Models for Understanding
• Engineers as philosophers, Part 1
• JuliusBrussee/caveman: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
• all LLMs are either claude-like or GPT-like method
• Can a biologist fix a radio?—Or, what I learned while studying apoptosis
• Revisiting the Platonic Representation Hypothesis: An Aristotelian View
• abus-aikorea voice-pro: Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
• DoTheEvo/ANGRYsearch: Linux file search, instant results as you type
• TIMIT Acoustic-Phonetic Continuous Speech Corpus - Linguistic Data Consortium
• Textualize/textual: The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
• AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
• Audio Explainable Artificial Intelligence: A Review
• Using an API to Retrieve and Process Every Playlist from a YouTube Account
• Relating Simple Sentence Representations in Deep Neural Networks and the Brain
• Neural Oscillations Carry Speech Rhythm through to Comprehension
• Marp: Markdown Presentation Ecosystem
• On Computational Positivism
• Dissecting neural computations in the human auditory pathway using deep neural networks for speech
• Beever-AI beever-atlas: Your First LLM-Wiki Conversation Knowledge Base
• Libribrain Datasets at Hugging Face
• LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory
• I Was Burning Through Claude Code’s Weekly Limit in 3 Days. Here’s How I Fixed It.
• check results drac slurm
• downloads and environment installations slurm
• pet Simple command-line snippet manager
• Larger and more instructable language models become less reliable
• INFERRING DNN-BRAIN ALIGNMENT USING REPRESENTATIONAL SIMILARITY ANALYSES CAN BE PROBLEMATIC
• Representation with a capital R: measuring functional alignment...
• Engineers as philosophers, Part 4
• A 204-subject multimodal neuroimaging dataset to study language processing
• A unified acoustic-to-speech-to-language embedding space captures the neural basis of natural language processing in everyday conversations - Nature Human Behaviour
• Markdown conversion with uv
• Brain-Score - Which Artificial Neural Network for Object Recognition is most Brain-Like?
• Revisiting the Platonic Representation Hypothesis An Aristotelian View
• Robust Speech Recognition via Large-Scale Weak Supervision
• Improving Audio Explanations Using Audio Language Models
• microsoft VibeVoice Open-Source Frontier Voice AI
• LLMs Know They’re Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
• Bella Fascendini on X: "New paper! w/@cocosci_lab 🧵Can large language models reason flexibly, or have they learned what reasoning looks like? We introduce a new paradigm to test this question—the riddle riddle—and find that humans and LLMs show opposite patterns of performance. 📜"
• Interpreting OpenAI’s Whisper
• Neural oscillations track natural but not artificial fast speech - Novel insights from speech-brain coupling using MEG
• llm-wiki
• Artificial Intelligence, Interactive Measurements, and Assemblage Theory
• UVX PDF to MD
• Brains and algorithms partially converge in natural language processing
• Introducing MEG-MASC a high-quality magneto-encephalography dataset for evaluating natural speech processing
• MemPalace mempalace: The best-benchmarked open-source AI memory system. And it's free.
• rebasing rebase pyprep .github CONTRIBUTING.md at 902b1391aa681a3c6d6ab2a8f9462a4f5f83d491
• openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision
• Symphonie des oscillations cérébrales lors de la perception de la parole. études comportementale et en magnétoencéphalographie chez les enfants neurotypiques et dysphasiques
• Artificial Intelligence as Sorcery
• What are some SOTA alternatives to SAEs for mechanistic interpretability
• Many but not all deep neural network audio models capture brain responses and exhibit correspondence between model stages and brain regions
• What Do Speech Foundation Models Not Learn About Speech?
• Commentary Investigating the concept of representation in the neural and psychological sciences
• Engineers as philosophers, Part 3
• safishamsi graphify: AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, OpenClaw, Factory Droid, Trae, Google Antigravity). Turn any folder of code, docs, papers, images, or videos into a queryable knowledge graph
• 10 CLI Tools That Made the Biggest Impact On Transforming My Terminal-Based Workflow
• Deciphering language processing in the human brain through LLM representations
• Lost in Translation The Algorithmic Gap Between LMs and the Brain
• GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics
• Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers
• 'This is a platform shift': Jensen Huang says the traditional computing stack will never look the same because of AI
• There Will Be a Scientific Theory of Deep Learning
• Language models transmit behavioural traits through hidden signals in data
• Digital garden
• The CLI is the path to AI autonomy, for now.
• Engineers as philosophers, Part 2
• DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking
• Could a Neuroscientist Understand a Microprocessor?
• List of markdown presentation tools
• guidelabs-steerling Interpretable Causal Diffusion Language Models
• jamiepine-voicebox-The open-source voice synthesis studio
• A 10-hour within-participant magnetoencephalography narrative dataset to test models of language comprehension
• A Matplotlib maintainer closed a pull request made by an AI. The "AI" went on to publish a rant-filled blog post about the "human" maintainer.
• Interpretable Embeddings of Speech Explain and Enhance the Brain Encoding Performance of Audio Models
• agarrharr awesome-cli-apps A curated list of command line apps
• Introducing talkie: a 13B vintage language model from 1930
• Mosh: the mobile shell
• Perceptual Musical Features for Interpretable Audio Tagging
• jordan-gibbs/hyperresearch: Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.
• NVIDIA-NeMo NeMo - A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
• Representation with a capital 'R': measuring functional alignment (openreview)
• obsidian-second-brain: Claude Code skill for Obsidian. Turn your vault into a living AI-first second brain. 31 commands, vault-first research, scheduled agents.
• garrytan gbrain: Garry's Opinionated OpenClaw/Hermes Agent Brain
• Whisper-KAN for Speech Emotion Recognition
• robert-mcdermott ai-knowledge-graph: AI Powered Knowledge Graph Generator
• libribrain2 (update of dataset it seems)
• Probing Whisper for Dysarthric Speech in Detection and Assessment
• Designing synthetic datasets for the real world: Mechanism design and reasoning from first principles
• arkaroy14 waydroid_network_spoof: Xposed Module to Spoof Wifi or Cellular to waydroid running on ethernet
• AI-generated synthetic neurons speed up brain mapping
• The World Inside Neural Networks
• RAG, LLM Wiki, or Gbrain? How Your Agent Remembers Changes Everything
• Mother of unification studies, a 204-subject multimodal neuroimaging dataset to study language processing
• Evergreen notes